logoalt Hacker News

cyanydeez • today at 8:02 PM • 2 replies • view on HN

If I could find a vendor that scales stupid simple qwen3.8-flash-next quant 4 that only needs 40GB VRAM and PLE, but is blazing fast.

I think most of ya'll drive those 70's gas guzzling death machines while honda, toyotas, etc are right around the corner to eat your lunch because, man, these low rate models absolutely cook.


Replies

girvo • today at 8:44 PM

Nvidia’s QAD NVFP4 quant is close to this on Blackwell gear.

edoceo • today at 8:35 PM

Can you roll your own on some CloudVM for a reasonable price?